testbatting2007 <- read.csv("D:\\Vishal\\III year\\Data Analytics\\Assignment II\\Player Ratings\\2007testbattingrating.csv")
testbatting2008 <- read.csv("D:\\Vishal\\III year\\Data Analytics\\Assignment II\\Player Ratings\\2008testbattingrating.csv")
testbatting2009 <- read.csv("D:\\Vishal\\III year\\Data Analytics\\Assignment II\\Player Ratings\\2009testbattingrating.csv")
testbatting2010 <- read.csv("D:\\Vishal\\III year\\Data Analytics\\Assignment II\\Player Ratings\\2010testbattingrating.csv")
testbatting2011 <- read.csv("D:\\Vishal\\III year\\Data Analytics\\Assignment II\\Player Ratings\\2011testbattingrating.csv")
testbatting2012 <- read.csv("D:\\Vishal\\III year\\Data Analytics\\Assignment II\\Player Ratings\\2012testbattingrating.csv")
testbatting2013 <- read.csv("D:\\Vishal\\III year\\Data Analytics\\Assignment II\\Player Ratings\\2013testbattingrating.csv")
testbatting2014 <- read.csv("D:\\Vishal\\III year\\Data Analytics\\Assignment II\\Player Ratings\\2014testbattingrating.csv")
testbatting2015 <- read.csv("D:\\Vishal\\III year\\Data Analytics\\Assignment II\\Player Ratings\\2015testbattingrating.csv")
testbatting2016 <- read.csv("D:\\Vishal\\III year\\Data Analytics\\Assignment II\\Player Ratings\\2016testbattingrating.csv")
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
dataTestBatting <- bind_rows(testbatting2007, testbatting2008, testbatting2009, testbatting2010,
testbatting2011, testbatting2012, testbatting2013, testbatting2014,
testbatting2015, testbatting2016)
## Warning in bind_rows_(x, .id): Unequal factor levels: coercing to character
## Warning in bind_rows_(x, .id): binding character and factor vector,
## coercing into character vector
## Warning in bind_rows_(x, .id): binding character and factor vector,
## coercing into character vector
## Warning in bind_rows_(x, .id): binding character and factor vector,
## coercing into character vector
## Warning in bind_rows_(x, .id): binding character and factor vector,
## coercing into character vector
## Warning in bind_rows_(x, .id): binding character and factor vector,
## coercing into character vector
## Warning in bind_rows_(x, .id): binding character and factor vector,
## coercing into character vector
## Warning in bind_rows_(x, .id): binding character and factor vector,
## coercing into character vector
## Warning in bind_rows_(x, .id): binding character and factor vector,
## coercing into character vector
## Warning in bind_rows_(x, .id): binding character and factor vector,
## coercing into character vector
## Warning in bind_rows_(x, .id): binding character and factor vector,
## coercing into character vector
summary(dataTestBatting)
## Name Rating LogRating
## Length:1000 Min. :171.0 Min. :2.233
## Class :character 1st Qu.:330.0 1st Qu.:2.519
## Mode :character Median :454.0 Median :2.657
## Mean :485.4 Mean :2.653
## 3rd Qu.:632.2 3rd Qu.:2.801
## Max. :936.0 Max. :2.971
## NA's :1
library(VIM)
## Loading required package: colorspace
## Loading required package: grid
## Loading required package: data.table
##
## Attaching package: 'data.table'
## The following objects are masked from 'package:dplyr':
##
## between, first, last
## VIM is ready to use.
## Since version 4.0.0 the GUI is in its own package VIMGUI.
##
## Please use the package to use the new (and old) GUI.
## Suggestions and bug-reports can be submitted at: https://github.com/alexkowa/VIM/issues
##
## Attaching package: 'VIM'
## The following object is masked from 'package:datasets':
##
## sleep
aggr(dataTestBatting)

dataTestBatting <- dataTestBatting %>%
group_by(Name) %>%
summarise(avg = mean(Rating))
set.seed(20)
batcluster <- kmeans(dataTestBatting[, 2], 5)
batcluster$cluster <- as.factor(batcluster$cluster)
library(DT)
library(ggplot2)
ggplot(dataTestBatting, aes(dataTestBatting$Name, avg, color = batcluster$cluster)) +
geom_point(size = 2) +
scale_color_manual(labels = c("Good", "Best", "Useless", "Better", "Average"), values = c("blue", "red", "green", "magenta", "black")) +
theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
ggtitle("Test Batting Ratings(2007-2016)")

dat <- arrange(dataTestBatting, desc(avg)) %>%
mutate(rank = 1:nrow(dataTestBatting))
dataTestBatting <- merge(dataTestBatting, dat, by = "Name")
dataTestBatting
## Name avg.x avg.y rank
## 1 Aftab Ahmed 315.0000 315.0000 189
## 2 Mohammad Hafeez 344.0000 344.0000 170
## 3 Raqibul Hasan 235.0000 235.0000 242
## 4 A B de Villiers 773.9000 773.9000 8
## 5 A Barath 356.5000 356.5000 161
## 6 A C Gilchrist 662.0000 662.0000 31
## 7 A C Voges 626.0000 626.0000 41
## 8 A D Hales 405.0000 405.0000 139
## 9 A D Mathews 611.7143 611.7143 45
## 10 A Flintoff 505.0000 505.0000 77
## 11 A G Prince 676.8000 676.8000 26
## 12 A J Doolan 335.0000 335.0000 178
## 13 A J Redmond 255.6667 255.6667 229
## 14 A J Strauss 654.8333 654.8333 33
## 15 A Kumble 277.5000 277.5000 215
## 16 A Lyth 285.0000 285.0000 208
## 17 A M Rahane 644.0000 644.0000 36
## 18 A Mishra 248.0000 248.0000 233
## 19 A N Cook 711.1000 711.1000 17
## 20 A N Petersen 465.8000 465.8000 97
## 21 A Symonds 586.5000 586.5000 53
## 22 Abdur Razzak 171.0000 171.0000 265
## 23 Abdur Rehman 224.0000 224.0000 252
## 24 Adnan Akmal 339.5000 339.5000 175
## 25 Aftab Ahmed 314.5000 314.5000 191
## 26 Ahmed Shehzad 488.0000 488.0000 88
## 27 Asad Shafiq 588.6667 588.6667 51
## 28 Azhar Ali 671.3333 671.3333 29
## 29 B A Stokes 497.6667 497.6667 83
## 30 B B B B B S M Warnapura 453.0000 453.0000 106
## 31 B B B B S M Warnapura 349.0000 349.0000 164
## 32 B B McCullum 603.7778 603.7778 48
## 33 B J Haddin 496.1250 496.1250 85
## 34 B J Hodge 454.0000 454.0000 105
## 35 B J Watling 430.1429 430.1429 122
## 36 B K G Mendis 466.0000 466.0000 96
## 37 B Kumar 275.5000 275.5000 216
## 38 B Lee 309.5000 309.5000 192
## 39 B P Nash 463.3333 463.3333 100
## 40 B R M Taylor 386.0000 386.0000 149
## 41 C A Pujara 631.2000 631.2000 38
## 42 C D Cumming 406.0000 406.0000 136
## 43 C F K van Wyk 331.0000 331.0000 179
## 44 C H Gayle 628.0000 628.0000 39
## 45 C H Morris 254.0000 254.0000 231
## 46 C J Anderson 382.6667 382.6667 152
## 47 C J L Rogers 669.5000 669.5000 30
## 48 C K Kapugedera 307.6667 307.6667 194
## 49 C R Brathwaite 347.0000 347.0000 166
## 50 C R Ervine 227.0000 227.0000 249
## 51 C R Woakes 231.0000 231.0000 244
## 52 D A Warner 703.6000 703.6000 20
## 53 D Elgar 427.2500 427.2500 123
## 54 D G Brownlie 449.0000 449.0000 108
## 55 D Ganga 406.0000 406.0000 137
## 56 D J G Sammy 302.1667 302.1667 198
## 57 D J J Bravo 548.0000 548.0000 64
## 58 D L Vettori 549.5000 549.5000 62
## 59 D M Bravo 593.0000 593.0000 50
## 60 D P M Jayawardene 745.5000 745.5000 11
## 61 D R Flynn 323.6000 323.6000 184
## 62 D Ramdin 405.3000 405.3000 138
## 63 D S Smith 315.3000 315.3000 188
## 64 D W Steyn 229.6667 229.6667 247
## 65 E Chigumbura 231.0000 231.0000 245
## 66 E J G Morgan 303.0000 303.0000 197
## 67 E J M Cowan 475.5000 475.5000 91
## 68 F D M Karunaratne 440.0000 440.0000 114
## 69 F du Plessis 626.7500 626.7500 40
## 70 Faisal Iqbal 340.6667 340.6667 172
## 71 G C Smith 732.1429 732.1429 16
## 72 G Gambhir 583.5000 583.5000 54
## 73 G P Swann 352.0000 352.0000 162
## 74 G S Ballance 479.0000 479.0000 90
## 75 H A P W Jayawardena 401.7000 401.7000 142
## 76 H D R Thirimanne 340.2500 340.2500 174
## 77 H D Rutherford 338.2500 338.2500 177
## 78 H H Gibbs 581.0000 581.0000 55
## 79 H M Amla 740.7000 740.7000 13
## 80 H M R Herath 214.0000 214.0000 258
## 81 H Masakadza 392.0000 392.0000 148
## 82 Habibul Bashar 519.0000 519.0000 71
## 83 Harbhajan Singh 277.7778 277.7778 214
## 84 I J L Trott 688.6000 688.6000 24
## 85 I K Pathan 395.0000 395.0000 145
## 86 I R Bell 638.1000 638.1000 37
## 87 Imran Farhat 498.8333 498.8333 80
## 88 Imrul Kayes 318.1429 318.1429 186
## 89 Inzamam-ul-Haq 735.0000 735.0000 15
## 90 J A Burns 421.5000 421.5000 126
## 91 J A Rudolph 363.8333 363.8333 158
## 92 J Blackwood 468.3333 468.3333 95
## 93 J C Buttler 420.0000 420.0000 127
## 94 J D P Oram 537.0000 537.0000 67
## 95 J D Ryder 539.0000 539.0000 66
## 96 J D S Neesham 437.6667 437.6667 116
## 97 J E C Franklin 279.5000 279.5000 212
## 98 J E Root 693.7500 693.7500 22
## 99 J E Taylor 237.0000 237.0000 239
## 100 J H Kallis 814.4286 814.4286 5
## 101 J K Silva 554.3333 554.3333 59
## 102 J L Pattinson 274.5000 274.5000 217
## 103 J M Bairstow 464.0000 464.0000 99
## 104 J M How 443.0000 443.0000 110
## 105 J O Holder 384.3333 384.3333 151
## 106 J P Duminy 433.2500 433.2500 118
## 107 Javed Omar 372.0000 372.0000 157
## 108 Junaid Siddique 408.2000 408.2000 135
## 109 K A Edwards 416.3333 416.3333 131
## 110 K C Brathwaite 403.2000 403.2000 140
## 111 K C Sangakkara 861.1111 861.1111 1
## 112 K D K Vithanage 254.6667 254.6667 230
## 113 K K K K K K D Karthik 359.3333 359.3333 160
## 114 K L Rahul 265.0000 265.0000 223
## 115 K O A Powell 351.5000 351.5000 163
## 116 K P Pietersen 741.1429 741.1429 12
## 117 K S Williamson 646.6667 646.6667 35
## 118 K T G Prasad 200.0000 200.0000 261
## 119 Kamran Akmal 565.0000 565.0000 57
## 120 Khaled Masud 289.0000 289.0000 206
## 121 Khurram Manzoor 307.5000 307.5000 195
## 122 L D Chandimal 530.2000 530.2000 69
## 123 L M P Simmons 237.0000 237.0000 240
## 124 L P C Silva 472.0000 472.0000 94
## 125 L R Johnson 379.5000 379.5000 154
## 126 L R Taylor 702.1111 702.1111 21
## 127 L Ronchi 417.5000 417.5000 129
## 128 L Vincent 515.0000 515.0000 73
## 129 Litton Das 267.5000 267.5000 222
## 130 M A Starc 339.5000 339.5000 176
## 131 M A Vermeulen 292.0000 292.0000 205
## 132 M D Craig 425.0000 425.0000 124
## 133 M D K J Perera 346.0000 346.0000 168
## 134 M D K Perera 278.0000 278.0000 213
## 135 M E K Hussey 759.0000 759.0000 9
## 136 M F Maharoof 243.0000 243.0000 236
## 137 M G Johnson 330.5000 330.5000 180
## 138 M G Vandort 402.0000 402.0000 141
## 139 M J Clarke 758.8889 758.8889 10
## 140 M J Guptill 418.2500 418.2500 128
## 141 M J North 472.5000 472.5000 93
## 142 M J Prior 555.1250 555.1250 58
## 143 M J Santner 297.0000 297.0000 202
## 144 M J Vijay 462.3750 462.3750 101
## 145 M L Hayden 831.0000 831.0000 4
## 146 M Morkel 245.0000 245.0000 235
## 147 M N Samuels 475.3000 475.3000 92
## 148 M N Waller 279.6667 279.6667 211
## 149 M P Vaughan 554.0000 554.0000 60
## 150 M R Marsh 272.0000 272.0000 218
## 151 M S Atapattu 503.0000 503.0000 78
## 152 M S Dhoni 566.2500 566.2500 56
## 153 M S Sinclair 385.3333 385.3333 150
## 154 M S Wade 349.0000 349.0000 165
## 155 M V Boucher 508.2000 508.2000 76
## 156 Mahmudullah 417.4286 417.4286 130
## 157 Mashrafe Mortaza 251.0000 251.0000 232
## 158 Misbah ul Haq 679.1111 679.1111 25
## 159 Moeen Ali 395.6667 395.6667 144
## 160 Mohammad Ashraful 392.6667 392.6667 147
## 161 Mohammad Hafeez 452.7778 452.7778 107
## 162 Mohammad Rafiq 318.0000 318.0000 187
## 163 Mohammad Yousuf 854.5000 854.5000 2
## 164 Mominul Haque 549.0000 549.0000 63
## 165 Mushfiqur Rahim 513.5000 513.5000 74
## 166 N D McKenzie 454.5000 454.5000 104
## 167 N Deonarine 363.7500 363.7500 159
## 168 N M Hauritz 302.0000 302.0000 199
## 169 N M Lyon 193.0000 193.0000 262
## 170 N R D Compton 329.2500 329.2500 183
## 171 N T Paranavitana 465.6667 465.6667 98
## 172 N V Ojha 221.0000 221.0000 255
## 173 Naeem Islam 240.0000 240.0000 238
## 174 Nasir Hossain 441.4000 441.4000 112
## 175 Nazimuddin 269.0000 269.0000 221
## 176 O A Shah 228.0000 228.0000 248
## 177 P A Jaques 588.0000 588.0000 52
## 178 P A Patel 281.5000 281.5000 209
## 179 P D Collingwood 662.0000 662.0000 32
## 180 P G Fulton 260.0000 260.0000 227
## 181 P J Hughes 501.8000 501.8000 79
## 182 P M Nevill 347.0000 347.0000 167
## 183 P M Siddle 263.5000 263.5000 225
## 184 P Utseya 206.0000 206.0000 260
## 185 Q de Kock 434.5000 434.5000 117
## 186 R A Jadeja 299.0000 299.0000 200
## 187 R Ashwin 442.2000 442.2000 111
## 188 R Dravid 710.4000 710.4000 18
## 189 R G Sharma 498.0000 498.0000 81
## 190 R J Harris 270.0000 270.0000 220
## 191 R J Peterson 258.0000 258.0000 228
## 192 R J Sidebottom 183.0000 183.0000 264
## 193 R McLaren 247.0000 247.0000 234
## 194 R N Lewis 222.0000 222.0000 254
## 195 R O Hinds 218.0000 218.0000 257
## 196 R R Sarwan 623.8000 623.8000 42
## 197 R S Bopara 341.0000 341.0000 171
## 198 R S Morton 297.0000 297.0000 203
## 199 R T Ponting 779.6667 779.6667 7
## 200 R W Chakabva 242.0000 242.0000 237
## 201 Rajin Saleh 441.0000 441.0000 113
## 202 Raqibul Hasan 235.0000 235.0000 243
## 203 S B Styris 509.0000 509.0000 75
## 204 S C Cook 439.0000 439.0000 115
## 205 S C Ganguly 607.5000 607.5000 46
## 206 S C J Broad 375.1111 375.1111 155
## 207 S Chanderpaul 831.2500 831.2500 3
## 208 S Chattergoon 191.0000 191.0000 263
## 209 S D Hope 236.0000 236.0000 241
## 210 S D Robson 305.0000 305.0000 196
## 211 S Dhawan 495.5000 495.5000 86
## 212 S E Marsh 394.2500 394.2500 146
## 213 S J Benn 230.0000 230.0000 246
## 214 S K Raina 308.1667 308.1667 193
## 215 S M Katich 595.2500 595.2500 49
## 216 S M Pollock 488.0000 488.0000 89
## 217 S O Dowrich 263.5000 263.5000 226
## 218 S P D Smith 619.5000 619.5000 44
## 219 S P Fleming 674.0000 674.0000 27
## 220 S R Tendulkar 736.7143 736.7143 14
## 221 S R Watson 532.1429 532.1429 68
## 222 S T Jayasuriya 498.0000 498.0000 82
## 223 S T R Binny 224.0000 224.0000 253
## 224 S van Zyl 330.5000 330.5000 181
## 225 Salman Butt 461.2500 461.2500 102
## 226 Sarfraz Ahmed 539.6667 539.6667 65
## 227 Shahid Afridi 457.5000 457.5000 103
## 228 Shahriar Nafees 430.8333 430.8333 121
## 229 Shakib Al Hasan 529.7778 529.7778 70
## 230 Shamsur Rahman 280.0000 280.0000 210
## 231 Shan Masood 271.0000 271.0000 219
## 232 Shoaib Malik 415.3333 415.3333 132
## 233 Shuvagata Hom 214.0000 214.0000 259
## 234 Sikandar Raza 381.0000 381.0000 153
## 235 T A M Siriwardana 431.0000 431.0000 119
## 236 T Bavuma 431.0000 431.0000 120
## 237 T G McIntosh 319.0000 319.0000 185
## 238 T G Southee 264.1429 264.1429 224
## 239 T M Dilshan 619.6667 619.6667 43
## 240 T M K Mawoyo 315.0000 315.0000 190
## 241 T Panyangara 226.0000 226.0000 250
## 242 T R Ambrose 374.0000 374.0000 156
## 243 T T Bresnan 293.0000 293.0000 204
## 244 T T Samaraweera 646.8333 646.8333 34
## 245 T Taibu 516.0000 516.0000 72
## 246 T W M Latham 497.0000 497.0000 84
## 247 Tamim Iqbal 552.6667 552.6667 61
## 248 Tanvir Ahmed 225.0000 225.0000 251
## 249 Taufeeq Umar 446.3750 446.3750 109
## 250 U T Khawaja 340.3333 340.3333 173
## 251 Umar Akmal 605.5000 605.5000 47
## 252 V D Philander 401.5000 401.5000 143
## 253 V Kohli 674.0000 674.0000 28
## 254 V Sehwag 709.1667 709.1667 19
## 255 V Sibanda 330.0000 330.0000 182
## 256 V V S Laxman 690.2000 690.2000 23
## 257 W P Saha 288.0000 288.0000 207
## 258 W P U Vaas 409.0000 409.0000 134
## 259 W U Tharanga 344.7778 344.7778 169
## 260 Wasim Jaffer 495.0000 495.0000 87
## 261 X M Marshall 299.0000 299.0000 201
## 262 Yasir Hameed 412.7500 412.7500 133
## 263 Younis Khan 788.2000 788.2000 6
## 264 Yuvraj Singh 423.1667 423.1667 125
## 265 Zaheer Khan 221.0000 221.0000 256
library(plotly)
##
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
##
## last_plot
## The following object is masked from 'package:stats':
##
## filter
## The following object is masked from 'package:graphics':
##
## layout
p <- plot_ly(dataTestBatting, x = ~Name, y = ~avg.x, type = 'scatter',
mode = 'markers', color = batcluster$cluster,
text = ~paste('Rank: ', rank))
p